# Claude Opus 4.6 vs Claude Sonnet 5.5

> Side-by-side benchmark comparison for Claude Opus 4.6 and Claude Sonnet 5.5 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/claude-opus-4-6-vs-claude-sonnet-5-5
- Last updated: September 28, 2026

- Shared sourced benchmarks: 3
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.7

## Quick Verdict

Evidence is too thin for a benchmark verdict: Claude Opus 4.6 and Claude Sonnet 5.5 share only 3 sourced benchmark rows.

## Summary

- Only 3 shared sourced benchmark rows are available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- Claude Sonnet 5.5 has the lower published output-token price.

## Model Snapshot

| Property | Claude Opus 4.6 | Claude Sonnet 5.5 |
|----------|----------|----------|
| Creator | Anthropic | Anthropic |
| Type | Proprietary | Proprietary |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 1M | 1M |
| Independent public score (not head-to-head) | 63.61 | 80.49 |
| Benchmarks Covered | 34 | 47 |
| Pricing (input/output) | $5.00 / $25.00 | $2.00 / $10.00 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Claude Opus 4.6 public-lane score: 44.3 (Supported · #40/111)
- Claude Sonnet 5.5 public-lane score: 66.1 (Supported · #10/111)

| Benchmark | Claude Opus 4.6 | Claude Sonnet 5.5 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 65.4% | Coming soon | Coming soon |
| BrowseComp | 83.7% | Coming soon | Coming soon |
| OSWorld-Verified | 72.7% | Coming soon | Coming soon |
| Claw-Eval | 70.4% | Coming soon | Coming soon |
| DeepSearchQA | 73.7% | Coming soon | Coming soon |
| CyberGym | 66.6% | Coming soon | Coming soon |
| Gert Labs | 61.85% | Coming soon | Coming soon |
| ResearchClawBench | 19.9% | Coming soon | Coming soon |
| JobBench | 36.7% | Coming soon | Coming soon |
| ApprenticeBench | 5% | Coming soon | Coming soon |
| Terminal-Bench 4.0 | Coming soon | 70.60% | Coming soon |
| HLE w/ tools | Coming soon | 64.5% | Coming soon |
| DRACO | Coming soon | 87.0% | Coming soon |
| Terminal-Bench-Science 0.1 | Coming soon | 59.9% | Coming soon |
| LAB all-pass (Harvey held-out) | Coming soon | 10.0% | Coming soon |
| LAB criterion-pass (Harvey held-out) | Coming soon | 93.1% | Coming soon |
| Toolathlon Verified Pass@3 | Coming soon | 85.2% | Coming soon |
| Toolathlon Verified Pass³ | Coming soon | 68.5% | Coming soon |
| Toolathlon Verified avg. turns | Coming soon | 31.6 turns | Coming soon |
| AutomationBench (Zapier 1.0.6) | Coming soon | 44.7% | Coming soon |
| Toolathlon-Verified | Coming soon | 77.8% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- Claude Opus 4.6 public-lane score: 49.5 (Supported · #39/136)
- Claude Sonnet 5.5 public-lane score: 79.6 (Estimated · #3/136)

| Benchmark | Claude Opus 4.6 | Claude Sonnet 5.5 | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 80.8% | Coming soon | Coming soon |
| SWE-bench Verified* | 75.6% | Coming soon | Coming soon |
| LiveCodeBench Pro | 70.7% | Coming soon | Coming soon |
| SWE-bench Pro | 53.4% | 81.3% | Claude Sonnet 5.5 |
| SWE-Rebench | 65.3% | Coming soon | Coming soon |
| React Native Evals | 84.1% | Coming soon | Coming soon |
| Vibe Code Bench | 57.57% | Coming soon | Coming soon |
| FrontierCode 1.1 Main | 26.9% | 46.2% | Claude Sonnet 5.5 |
| cursorBench40 | Coming soon | 55.5% | Coming soon |
| SWE Multilingual | Coming soon | 90.3% | Coming soon |
| SWE Multimodal | Coming soon | 54.3% | Coming soon |
| DeepSWE | Coming soon | 71.0% | Coming soon |
| FrontierCode 1.1 Extended | Coming soon | 59.1% | Coming soon |
| ProgramBench | Coming soon | 79.7% | Coming soon |
| FrontierSWE v2 | Coming soon | 61.9% | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- Claude Opus 4.6 public-lane score: 68.3 (Unranked · 2 rankable rows)
- Claude Sonnet 5.5 public-lane score: 79.2 (#7/27)

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- Claude Opus 4.6 public-lane score: 60.6 (#30/50)
- Claude Sonnet 5.5 public-lane score: 83.3 (Unranked · 7 rankable rows)

| Benchmark | Claude Opus 4.6 | Claude Sonnet 5.5 | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | 77.3% | Coming soon | Coming soon |
| ERQA | 51.6% | Coming soon | Coming soon |
| ScreenSpot Pro | 83.1% | Coming soon | Coming soon |
| MedXpertQA (MM) | 64.8% | Coming soon | Coming soon |
| Chartography (no tools) | Coming soon | 61.6% | Coming soon |
| Chartography (tools) | Coming soon | 90.2% | Coming soon |
| BenchCAD Vision2Code (no tools) | Coming soon | 0.747 | Coming soon |
| BenchCAD Vision2Code (tools) | Coming soon | 0.963 | Coming soon |
| Biomedical image analysis | Coming soon | 72.2% | Coming soon |
| OfficeQA | Coming soon | 76.9% | Coming soon |
| OfficeQA Pro | Coming soon | 65.6% | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- Claude Opus 4.6 public-lane score: 58.7 (Estimated · #39/160)
- Claude Sonnet 5.5 public-lane score: 80.9 (Supported · #6/160)

| Benchmark | Claude Opus 4.6 | Claude Sonnet 5.5 | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 91.3% | Coming soon | Coming soon |
| GPQA-D | 89.2% | Coming soon | Coming soon |
| SuperGPQA | 95% | Coming soon | Coming soon |
| MMLU-Pro | 82% | Coming soon | Coming soon |
| MMLU-Pro (Arcee) | 89.1% | Coming soon | Coming soon |
| HLE | 53% | Coming soon | Coming soon |
| HLE w/o tools | 40% | 56.9% | Claude Sonnet 5.5 |
| HealthBench Hard | 14.8% | Coming soon | Coming soon |
| MedXpertQA (Text) | 52.1% | Coming soon | Coming soon |
| HealthBench (raw) | Coming soon | 69.4% | Coming soon |
| HealthBench (length-adjusted) | Coming soon | 65.4% | Coming soon |
| HealthBench Professional (raw) | Coming soon | 77.1% | Coming soon |
| HealthBench Professional | Coming soon | 69.2% | Coming soon |
| BioMysteryBench (human-solvable) | Coming soon | 89.2% | Coming soon |
| BioMysteryBench (human-difficult) | Coming soon | 44.7% | Coming soon |
| SpatialBench Verified | Coming soon | 72.5% | Coming soon |
| SingleCellBench | Coming soon | 59.1% | Coming soon |
| Protein Design | Coming soon | 51.0% | Coming soon |
| Morphology-to-molecule matching | Coming soon | 25.0% | Coming soon |
| Medicinal chemistry | Coming soon | 65.3% | Coming soon |
| Protein Design library ranking | Coming soon | 54.8% | Coming soon |
| De novo protein-binder design | Coming soon | 82.3% | Coming soon |
| Protocols (troubleshooting) | Coming soon | 67.3% | Coming soon |
| Protocols (understanding) | Coming soon | 66.6% | Coming soon |

### Multilingual

- Winner: Insufficient shared evidence
- Claude Opus 4.6 public-lane score: Coming soon
- Claude Sonnet 5.5 public-lane score: Coming soon

| Benchmark | Claude Opus 4.6 | Claude Sonnet 5.5 | Winner |
|-----------|-----------|-----------|--------|
| GMMLU | Coming soon | 92.1% | Coming soon |
| MILU | Coming soon | 91.6% | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- Claude Opus 4.6 public-lane score: 51 (#79/124)
- Claude Sonnet 5.5 public-lane score: Coming soon

### Mathematics

- Winner: Insufficient shared evidence
- Claude Opus 4.6 public-lane score: 58.5 (Unranked · 3 rankable rows)
- Claude Sonnet 5.5 public-lane score: Coming soon

| Benchmark | Claude Opus 4.6 | Claude Sonnet 5.5 | Winner |
|-----------|-----------|-----------|--------|
| AIME25 (Arcee) | 99.8% | Coming soon | Coming soon |
| FrontierMath v2 (Tiers 1-3) | 40.700% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 22.900% | Coming soon | Coming soon |
| ArXivMath Aug. 2026 (no tools) | Coming soon | 86.8% | Coming soon |
| ArXivMath Aug. 2026 (tools) | Coming soon | 95.2% | Coming soon |

## FAQ

### Is there enough evidence to pick between Claude Opus 4.6 and Claude Sonnet 5.5?

Not yet. The models share only 3 sourced benchmark rows, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [Claude Opus 4.6 vs Claude Opus 4.6 (Adaptive)](/compare/claude-opus-4-6-vs-claude-opus-4-6-thinking)
- [Claude Sonnet 5.5 vs Claude Opus 4.6 (Adaptive)](/compare/claude-opus-4-6-thinking-vs-claude-sonnet-5-5)
- [Claude Opus 4.6 vs GPT-6 Astra](/compare/claude-opus-4-6-vs-gpt-6-astra)
- [Claude Sonnet 5.5 vs GPT-6 Astra](/compare/claude-sonnet-5-5-vs-gpt-6-astra)

## Explore More

- [Claude Opus 4.6 profile](/models/claude-opus-4-6)
- [Claude Sonnet 5.5 profile](/models/claude-sonnet-5-5)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)